© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 34738
    Prev
    Next
    INDEX
    Explanations

    LED pin definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kish
    -0.09
    masked
    -0.08
    idor
    -0.08
     currents
    -0.08
     OTP
    -0.08
    OTP
    -0.08
     Immediate
    -0.08
     ANSI
    -0.08
     masked
    -0.08
     PID
    -0.08
    POSITIVE LOGITS
     pin
    0.20
     pins
    0.16
     Pin
    0.16
    pin
    0.16
    Pin
    0.15
     port
    0.15
     ground
    0.12
    å¼ķ
    0.11
     unused
    0.11
    port
    0.11
    Activations Density 0.031%

    No Known Activations